CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azsdk-common-pipeline-analysis

Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdk_analyze_pipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in CI", "analyze pipeline", "debug SDK pipeline". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing, applying code fixes (instead use azsdk-common-pipeline-fixer). INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_get_pipeline_llm_artifacts, azure-sdk-mcp:azsdk_get_failed_test_run_data, azure-sdk-mcp:azsdk_get_failed_test_case_data, azure-sdk-mcp:azsdk_get_pr_checks, azure-sdk-mcp:azsdk_get_pipeline_status.

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable workflow with exact tool orchestration and good error-recovery guidance. The main defect is broken progressive disclosure: both linked reference files are missing from the bundle.

Suggestions

Add the missing references/output-format.md and references/failure-patterns.md files to the bundle, or inline their essential content and drop the links.

Fold the Troubleshooting checks (verify build ID, empty failed_pipeline_tests fallback) into the relevant steps as inline validation checkpoints.

State the analysis-only boundary once (in Rules) and reference it from the intro instead of repeating it three times.

DimensionReasoningScore

Conciseness

The body is lean and operational with no filler, but the analysis-only boundary is repeated three times (intro 'It does NOT apply fixes', Rules 'Analysis-only: never edit files', step 6 'Recommend azsdk-common-pipeline-fixer'), which is minor over-explanation that could be trimmed.

4 / 5

Actionability

Fully actionable instruction-only guidance: exact MCP tool names, exact parameters (failedTestRunsPath, artifact_file_path, testCaseTitle), a decision rule for per-file vs per-test calls, real build IDs in examples, and concrete fallbacks in Troubleshooting.

5 / 5

Workflow Clarity

Six steps are clearly sequenced with decision points and error recovery, but validation checkpoints ('verify the build ID is correct', the empty-artifacts fallback) sit in a separate Troubleshooting section rather than inline in the step sequence.

4 / 5

Progressive Disclosure

References are well-signaled and one level deep ('[output format](references/output-format.md)', '[failure patterns](references/failure-patterns.md)'), but neither referenced file exists in the bundle, so the navigation chain dead-ends and the disclosure structure cannot function.

3 / 5

Total

16

/

20

Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete capabilities, natural trigger phrases, explicit use/don't-use boundaries, and clear differentiation from the sibling fixer skill. The only weakness is that the capability list is slightly less comprehensive than the trigger coverage.

Suggestions

Fold one or two more capability verbs into the opening sentence (e.g., 'categorize failures and identify root causes with affected files/lines') to close the specificity gap.

Add a common phrasing like 'CI is red' or 'pipeline broke' among the USE FOR triggers to broaden natural-language coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis', 'interprets and formats' raw tool data, 'define the required output format') with minor gaps in coverage since categorization and root-cause detail live in the body rather than the description.

4 / 5

Completeness

Explicitly answers what ('Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis') and when (a 'USE FOR:' clause with concrete trigger phrases plus a 'DO NOT USE FOR' boundary), matching the top anchor exactly.

5 / 5

Trigger Term Quality

Six natural trigger phrases users would actually say ('pipeline failed', 'build failure', 'CI check failing', 'tests failing in CI', 'analyze pipeline', 'debug SDK pipeline') comprehensively cover the domain; no file extensions apply to this pipeline-analysis context.

5 / 5

Distinctiveness Conflict Risk

Scoped to Azure SDK CI/CD pipelines specifically, with explicit exclusions (local build issues, API design review, SDK publishing, applying fixes) and a handoff to the sibling fixer skill, giving it a clear niche with minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository

Azure/azure-sdk-for-net

Path

.github/skills/azsdk-common-pipeline-analysis/SKILL.md

Revision

c609269

Reviewed

Table of Contents

DiscoveryImplementationValidation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

Claim skill